SLAM Estimation in Dynamic Outdoor Environments: A Review

Abstract

This paper gives a review of the literature on Simultaneous Localization and Mapping (SLAM). SLAM has been intensively researched in recent years in the field of robotics and intelligent vehicles, many approaches have been proposed including occupancy grid mapping method (Bayesian, Dempster-Shafer and Fuzzy Logic), Localization estimation method (edge or point features based direct scan matching techniques, probabilistic likelihood, particle filter). In this paper, we classify SLAM approaches into three main categories: visual SLAM, Lidar SLAM and sensor fusion SLAM, while visual and lidar can also contain many types and levels, such as monocular camera, stereovision, laser scanner, radar and fusion of these sensors. A number of promising approaches and recent developments in this literature have been reviewed in this paper. To give a better understanding of performance difference, an implementation of Lidar SLAM is presented with comparative analysis result.